Can an arbitrarily intelligent reinforcement learning agent be kept under control by a human user? Or do agents with sufficient intelligence inevitably find ways to shortcut their reward signal? This question impacts how far reinforcement learning can be scaled, and whether alternative paradigms must be developed in order to build safe artificial general intelligence. In this paper, we use an intuitive yet precise graphical model called causal influence diagrams to formalize reward tampering problems. We also describe a number of modifications to the reinforcement learning objective that prevent incentives for reward tampering. We verify the solutions using recently developed graphical criteria for inferring agent incentives from causal influence diagrams. Along the way, we also compare corrigibility and self-preservation properties of the various solutions, and discuss how they can be combined into a single agent without reward tampering incentives.
Proposals for safe AGI systems are typically made at the level of frameworks, specifying how the components of the proposed system should be trained and interact with each other. In this paper, we model and compare the most promising AGI safety frameworks using causal influence diagrams. The diagrams show the optimization objective and causal assumptions of the framework. The unified representation permits easy comparison of frameworks and their assumptions. We hope that the diagrams will serve as an accessible and visual introduction to the main AGI safety frameworks.
Agents are systems that optimize an objective function in an environment. Together, the goal and the environment induce secondary objectives, incentives. Modeling the agent-environment interaction in graphical models called influence diagrams, we can answer two fundamental questions about an agent's incentives directly from the graph: (1) which nodes is the agent incentivized to observe, and (2) which nodes is the agent incentivized to influence? The answers tell us which information and influence points need extra protection. For example, we may want a classifier for job applications to not use the ethnicity of the candidate, and a reinforcement learning agent not to take direct control of its reward mechanism. Different algorithms and training paradigms can lead to different influence diagrams, so our method can be used to identify algorithms with problematic incentives and help in designing algorithms with better incentives.
One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task objective. This gives rise to the agent alignment problem: how do we create agents that behave in accordance with the user's intentions? We outline a high-level research direction to solve the agent alignment problem centered around reward modeling: learning a reward function from interaction with the user and optimizing the learned reward function with reinforcement learning. We discuss the key challenges we expect to face when scaling reward modeling to complex and general domains, concrete approaches to mitigate these challenges, and ways to establish trust in the resulting agents.
The development of Artificial General Intelligence (AGI) promises to be a major event. Along with its many potential benefits, it also raises serious safety concerns (Bostrom, 2014). The intention of this paper is to provide an easily accessible and up-to-date collection of references for the emerging field of AGI safety. A significant number of safety problems for AGI have been identified. We list these, and survey recent research on solving them. We also cover works on how best to think of AGI from the limited knowledge we have today, predictions for when AGI will first be created, and what will happen after its creation. Finally, we review the current public policy on AGI.
Search is a central problem in artificial intelligence, and breadth-first search (BFS) and depth-first search (DFS) are the two most fundamental ways to search. In this paper we derive estimates for average BFS and DFS runtime. The average runtime estimates can be used to allocate resources or judge the hardness of a problem. They can also be used for selecting the best graph representation, and for selecting the faster algorithm out of BFS and DFS. They may also form the basis for an analysis of more advanced search methods. The paper treats both tree search and graph search. For tree search, we employ a probabilistic model of goal distribution; for graph search, the analysis depends on an additional statistic of path redundancy and average branching factor. As an application, we use the results to predict BFS and DFS runtime on two concrete grammar problems and on the N-puzzle. Experimental verification shows that our analytical approximations come close to empirical reality.
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side effects, absent supervisor, reward gaming, safe exploration, as well as robustness to self-modification, distributional shift, and adversaries. To measure compliance with the intended safe behavior, we equip each environment with a performance function that is hidden from the agent. This allows us to categorize AI safety problems into robustness and specification problems, depending on whether the performance function corresponds to the observed reward function. We evaluate A2C and Rainbow, two recent deep reinforcement learning agents, on our environments and show that they are not able to solve them satisfactorily.
No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. We formalise this problem as a generalised Markov Decision Problem called Corrupt Reward MDP. Traditional RL methods fare poorly in CRMDPs, even under strong simplifying assumptions and when trying to compensate for the possibly corrupt rewards. Two ways around the problem are investigated. First, by giving the agent richer data, such as in inverse reinforcement learning and semi-supervised reinforcement learning, reward corruption stemming from systematic sensory errors may sometimes be completely managed. Second, by using randomisation to blunt the agent's optimisation, reward corruption can be partially managed under some assumptions.
We introduce a new count-based optimistic exploration algorithm for Reinforcement Learning (RL) that is feasible in environments with high-dimensional state-action spaces. The success of RL algorithms in these domains depends crucially on generalisation from limited training experience. Function approximation techniques enable RL agents to generalise in order to estimate the value of unvisited states, but at present few methods enable generalisation regarding uncertainty. This has prevented the combination of scalable RL algorithms with efficient exploration strategies that drive the agent to reduce its uncertainty. We present a new method for computing a generalised state visit-count, which allows the agent to estimate the uncertainty associated with any state. Our \phi-pseudocount achieves generalisation by exploiting same feature representation of the state space that is used for value function approximation. States that have less frequently observed features are deemed more uncertain. The \phi-Exploration-Bonus algorithm rewards the agent for exploring in feature space rather than in the untransformed state space. The method is simpler and less computationally expensive than some previous proposals, and achieves near state-of-the-art results on high-dimensional RL benchmarks.
Function optimisation is a major challenge in computer science. The No Free Lunch theorems state that if all functions with the same histogram are assumed to be equally probable then no algorithm outperforms any other in expectation. We argue against the uniform assumption and suggest a universal prior exists for which there is a free lunch, but where no particular class of functions is favoured over another. We also prove upper and lower bounds on the size of the free lunch.